Environment-Conditioned Tail Reweighting for Total Variation Invariant Risk Minimization

• URL: http://arxiv.org/abs/2601.22944v2
• Date: Mon, 02 Feb 2026 09:28:56 GMT
• Title: Environment-Conditioned Tail Reweighting for Total Variation Invariant Risk Minimization
• Authors: Yuanchao Wang, Zhao-Rong Lai, Tianqi Zhong, Fengnan Li,
• Abstract summary: Out-of-distribution (OOD) generalization is challenging when models simultaneously encounter correlation shifts across environments.<n>Existing invariant risk minimization (IRM) methods primarily address spurious correlations at the environment level.<n>We propose Environment-Conditioned Tail Reweighting for Total Variation Invariant Risk Minimization (ECTR), a unified framework that augments TV-based invariant learning with environment-conditioned tail reweighting.
• Score: 14.19414103184649
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Out-of-distribution (OOD) generalization remains challenging when models simultaneously encounter correlation shifts across environments and diversity shifts driven by rare or hard samples. Existing invariant risk minimization (IRM) methods primarily address spurious correlations at the environment level, but often overlook sample-level heterogeneity within environments, which can critically impact OOD performance. In this work, we propose Environment-Conditioned Tail Reweighting for Total Variation Invariant Risk Minimization (ECTR), a unified framework that augments TV-based invariant learning with environment-conditioned tail reweighting to jointly address both types of distribution shift. By integrating environment-level invariance with within-environment robustness, the proposed approach makes these two mechanisms complementary under mixed distribution shifts. We further extend the framework to scenarios without explicit environment annotations by inferring latent environments through a minimax formulation. Experiments across regression, tabular, time-series, and image classification benchmarks under mixed distribution shifts demonstrate consistent improvements in both worst-environment and average OOD performance.

Related papers

• Evolving Graph Learning for Out-of-Distribution Generalization in Non-stationary Environments [61.62036321848316]
  Graph neural networks (GNNs) have shown remarkable success in exploiting the spatial and temporal patterns on dynamic graphs.<n>Existing GNNs exhibit poor ability under distribution shifts, which is inevitable in dynamic scenarios.<n>This paper proposes Evolving Graph Learning framework for evolving graph generalization (Evoal) by environment-aware invariant pattern recognition.
  arXiv  Detail & Related papers  (2025-11-04T08:22:29Z)
• Robust Invariant Representation Learning by Distribution Extrapolation [3.5051814539447474]
  Invariant risk minimization (IRM) aims to enable out-of-distribution generalization in deep learning.<n>Existing approaches -- including IRMv1 -- adopt penalty-based single-level approximations.<n>A novel framework is proposed that enhances environmental diversity by augmenting the IRM penalty through synthetic distributional shifts.
  arXiv  Detail & Related papers  (2025-05-22T02:03:34Z)
• Unsupervised Invariant Risk Minimization [7.903539618132858]
  We propose a novel unsupervised framework for emphInvariant Risk Minimization (IRM)<n>Traditional IRM methods rely on labeled data to learn representations that are robust to distributional shifts across environments.<n>We introduce two methods within this framework: Principal Invariant Component Analysis (PICA), a linear method that extracts invariant directions under Gaussian assumptions, and Variational Invariant Autoencoder (VIAE), a deep generative model that disentangles environment-invariant and environment-dependent latent factors.
  arXiv  Detail & Related papers  (2025-05-18T17:54:23Z)
• Graph Invariant Learning with Subgraph Co-mixup for Out-Of-Distribution Generalization [51.913685334368104]
  We propose a novel graph invariant learning method based on invariant and variant patterns co-mixup strategy. Our method significantly outperforms state-of-the-art under various distribution shifts.
  arXiv  Detail & Related papers  (2023-12-18T07:26:56Z)
• Continual Invariant Risk Minimization [46.051656238770086]
  Empirical risk minimization can lead to poor generalization behavior on unseen environments if the learned model does not capture invariant feature representations. Invariant risk minimization (IRM) is a recent proposal for discovering environment-invariant representations.
  arXiv  Detail & Related papers  (2023-10-21T11:44:47Z)
• Balancing Fairness and Robustness via Partial Invariance [17.291131923335918]
  Invariant Risk Minimization (IRM) aims to learn invariant features from a set of environments for solving the out-of-distribution (OOD) problem. We argue for a partial invariance framework to mitigate the failure case. Our results show the capability of the partial invariant risk minimization to alleviate the trade-off between fairness and risk in certain settings.
  arXiv  Detail & Related papers  (2021-12-17T06:41:47Z)
• Learning Representations that Support Robust Transfer of Predictors [5.65658124285176]
  We introduce a robust estimation criterion -- transfer risk -- that is specifically geared towards optimizing transfer to new environments. Although inspired by IRM, we show that transfer risk serves as a better out-of-distribution generalization criterion.
  arXiv  Detail & Related papers  (2021-10-19T13:00:37Z)
• Robust Reconfigurable Intelligent Surfaces via Invariant Risk and Causal Representations [55.50218493466906]
  In this paper, the problem of robust reconfigurable intelligent surface (RIS) system design under changes in data distributions is investigated. Using the notion of invariant risk minimization (IRM), an invariant causal representation across multiple environments is used such that the predictor is simultaneously optimal for each environment. A neural network-based solution is adopted to seek the predictor and its performance is validated via simulations against an empirical risk minimization-based design.
  arXiv  Detail & Related papers  (2021-05-04T21:36:31Z)
• Empirical or Invariant Risk Minimization? A Sample Complexity Perspective [49.43806345820883]
  It is unclear when in-variant risk generalization (IRM) should be preferred over the widely-employed empirical risk minimization (ERM) framework. We find that depending on the type of data generation mechanism, the two approaches might have very different finite sample and behavior. We further investigate how different factors -- the number of environments, complexity of the model, and IRM penalty weight -- impact the sample complexity of IRM in relation to its distance from the OOD solutions.
  arXiv  Detail & Related papers  (2020-10-30T17:55:30Z)
• GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue [95.23775347605923]
  Building on the success of deep learning, Generative Adversarial Networks (GANs) provide a modern approach to learn a probability distribution from observed samples. GANs often suffer from the mode collapse issue where the generator fails to capture all existing modes of the input distribution. We take an information-theoretic approach and maximize a variational lower bound on the entropy of the generated samples to increase their diversity.
  arXiv  Detail & Related papers  (2020-09-24T19:34:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.